AI improvement prompts

اهو ڪيئن ڪم ڪري ٿو

Click تي data جا ٻه pieces combine ٿين ٿا:

• Finding — title، description، evidence، remediation، CWE — report سان اڳ ئي loaded.
• توهان جي codebase جو framework — scan جي discovery.tech-fingerprint findings مان detected (Next.js، React، Vue، Django، Express، Rails، Laravel، Flask). جڏهن framework detected نه ٿئي، generic recipe ڏانهن falls back (agent prompt پوءِ LLM کان repo state مان detect ڪرڻ پڇي ٿو).

Templates live in lib/scanner/fix-prompts.ts. The registry has check-specific guidance for crawlability, search presentation, semantic content, structured data, media, performance, accessibility, forms, mobile/i18n, runtime, owner journeys, and repo-quality issues. For everything else, the existing remediation field on the finding becomes the generic recipe.

Prompt ڪيئن ڏسڻ ۾ اچي ٿو

Fix the "Hero image is lazy-loaded and missing dimensions" finding on /pricing.

Issue: The largest above-the-fold image is marked loading="lazy" and has
no explicit width/height. That can delay LCP and create layout shift.

Codebase context: Next.js.

Recommended fix:
Use next/image or the existing image component with explicit width/height,
responsive sizes, meaningful alt text, and priority/fetchPriority for the
first major visual on the page.

Constraints:
- Don't break existing tests; run the test suite after the change.
- Match the codebase's existing style and lint config.
- Add a brief comment explaining the performance reasoning only where the
  fix would otherwise look arbitrary.
- If the fix needs a new dependency, install it via the project's
  package manager (npm / pnpm / pip / bundle / composer).

Reference: Core Web Vitals / Largest Contentful Paint guidance.

Supported frameworks

اسان framework-specific snippets هنن لاءِ surface ڪريون ٿا:

• Next.js، React، Vue، Nuxt، Svelte (frontend)
• Express، Fastify (Node.js backend)
• Django، Flask (Python)
• Ruby on Rails
• Laravel (PHP)
• ASP.NET Core (planned، اڄ generic ڏانهن fallback)

Framework detection best-effort آهي. اسان __NEXT_DATA__ tags، __NUXT__، hash cookies (laravel_session)، X-Powered-By headers، ۽ ڪجهه ٻيا signals sniff ڪريون ٿا. جيڪڏهن توهان custom framework هلائي رهيا آهيو، prompt generic recipe ڏانهن falls back ڪري ٿو ۽ agent توهان جي package.json مان ان کي figure out ڪري ٿو.

پنهنجي AI agent مان استعمال ڪريو

جيڪڏهن توهان MCP server wire up ڪيو آهي، ساڳيو prompt slash command طور exposed آهي. Claude Desktop مان:

/fixweb-fix finding_id=550e8400-e29b-41d4-a716-446655440000

The renderer looks up the finding, detects the framework from the parent scan when available, renders the templated prompt, and injects it into your conversation as the user message. No round-trip to our Claude API; templates are pure and free.

اسان هر click تي Claude کي ڇو نٿا hit ڪريون

Launch تي اسان هر click لاءِ Anthropic API call ڪرڻ تي غور ڪيو ته prompt کي codebase context سان refine ڪجي. اسان ائين نه ڪيو، ڇو ته:

• User جنهن agent ۾ paste ڪري ٿو ان وٽ اڳ ئي codebase context آهي — اهي Cursor / Claude Desktop استعمال ڪري رهيا آهن پنهنجي repo open سان.
• هر (check × framework) تي templating بغير per-click cost جي value جو ~80% cover ڪري ٿي.
• “Refine with AI for my codebase” opt-in پوءِ API fire ڪري سگهي ٿو جيڪڏهن users چاهين. اڄ نه.